Skip to main content
Glama
Flisk App Builder

Flisk App Builder

Official

logs

Read-only

Fetch a read-only, bounded snapshot of recent runtime and build output from the running stack to diagnose service failures. Narrow by service or source; call again for newer entries.

Instructions

A bounded snapshot of recent logs from the running stack (default the last 200 lines, at most 10000), returned as text. Read-only. Optionally select the project with projectPath. Not a stream: call it again for newer lines. Use status first to find which service is failing, then pass services to narrow the output and source runtime to skip image build output and read why it failed.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "logs"
  }
}

Input Schema

NameRequiredDescriptionDefault
tailNo
sinceNoOnly logs newer than this, for example 30s, 5m, 1h
sourceNoruntime: only what the services printed (where a crash cause such as an exception or a missing variable is); build: only image build steps. Omit for both.
servicesNoOnly these services
projectPathNoAbsolute path to the Flisk project root; run this operation from that directory.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.4.69
    • addedInput schema / properties / source
      Added value: +{
      +  "description": "runtime: only what the services printed (where a crash cause such as an exception or a missing variable is); build: only image build steps. Omit for both.",
      +  "enum": [
      +    "runtime",
      +    "build"
      +  ],
      +  "type": "string"
      +}
  2. First observedv1.4.17

TDQS

A4.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only and closed-world safety, and the description adds real context on top: default line count, upper bound, text return format, and the non-streaming polling model. It stops short of describing pagination/truncation signaling or how results are ordered, but the behavioral picture is solid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four dense sentences: purpose first, then safety, then the polling caveat, then the diagnostic workflow. Every clause carries information and none is redundant with the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-param, all-optional, read-only diagnostic tool with no output schema, the description supplies everything an agent needs: defaults, bounds, return type, and a triage path paired with the `status` sibling. No output schema means no gap in omitting return-value structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 80%, so most params are already documented, but the description adds rationale the schema lacks — notably the 200-line default for `tail` and why `source: runtime` matters (crash causes such as exceptions or missing variables). It adds genuine decision-relevant meaning rather than restating field names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — a bounded snapshot of recent logs from the running stack — and immediately names scope limits (default 200, max 10000) and return type (text). It explicitly distinguishes itself from its stream sibling by saying 'Not a stream: call it again for newer lines.'

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Names the concrete workflow: use `status` first to identify the failing service, then pass `services` to narrow and `source: runtime` to skip build output. It also gives the when-not rule (not a stream, re-invoke for new lines), leaving little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.